A5088434774- Educational Innovations and Technology
- Education and Critical Thinking Development
- Scientific Computing and Data Management
- Advanced Neural Network Applications
- Bluetooth and Wireless Communication Technologies
- Fault Detection and Control Systems
- Machine Learning in Healthcare
- Integrated Circuits and Semiconductor Failure Analysis
- CCD and CMOS Imaging Sensors
- UAV Applications and Optimization
- Knowledge Societies in the 21st Century
- E-Learning and Knowledge Management
- Robotic Path Planning Algorithms
- Underwater Vehicles and Communication Systems
- Communication and COVID-19 Impact
- Distributed Control Multi-Agent Systems
- Adversarial Robustness in Machine Learning
- Brain Tumor Detection and Classification
- Health and Lifestyle Studies
- Educational methodologies and cognitive development
- Opportunistic and Delay-Tolerant Networks
Universitat Politècnica de València
2020-2024
Universitat Politècnica de Catalunya
2022
United States Congress
2020
As we experience an unprecedented growth in the field of Unmanned Aerial Vehicles (UAVs), more and applications keep arising due to combination low cost flexibility provided by these flying devices, especially those multirrotor type. Within this field, solutions where several UAVs team-up create a swarm are gaining momentum as they enable perform sophisticated tasks, or accelerate task execution compared single-UAV alternative. However, advanced based on UAV swarms still lack significant...
Neural networks (NN) for image processing in embedded systems expose two conflicting requirements: increasing computing power needs as models become more complex and constrained resource budget. In order to alleviate this problems, model compression based on quantization pruning techniques are common. Derived then need fit reconfigurable such FPGAs the system work properly. paper, we present HLSinf, an open source framework development of custom NN accelerators which provides efficient...
Abstract Neural networks are widely used in critical environments such as healthcare, autonomous vehicles, or video surveillance. To ensure the safety of systems that rely on their functionality, it is essential to validate correct behaviour presence faults. This paper studies state-of-the-art neural network models with fault injection weights. For this purpose, we analyse sensitivity these and identify impact bit flips accuracy. mitigate effects faults, introduce two mechanisms leverage...
Interactive methods are a good resource for making students reason and think. This is because they favor open analysis hypotheses develop divergent thinking in STEMC subjects. The objectives: need to build knowledge from intersubjective relationships by studying working autonomously; the ability self-learning, publicize trends of perspective development with new methodologies order allow teachers enrich themselves these experiences. Applying conclusion that another means improve their level...